Abstract
The study of automatic music generation has led to the development of a variety of systems which incorporate different methods and technologies. However, it can be noted that many systems are evaluated by a comparison of its own performances and have limited objective evaluations conducted against other works in the field. This can be attributed to the general study of automatic music generation being weak in a framework for systematic discussion and comparison. In our study, we propose remodeling the interaction between humans and music-generation systems using a human-agent interaction model. Not only does this provide direction to a systematic discussion in the field, but also shows music-generation research lacks in definition of the environment it is meant to affect. We discuss some potential guidelines which could be applied to future music generation research to overcome this weakness.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
